Grasp Programming by Demonstration: A task-based quality measure

This paper addresses the issue of how Programming by Demonstration can assist the development of task-related grasping capabilities in a robotic system. Finding a proper quality measure for the evaluation of grasping tasks is a crucial topic for service robots. While classical grasp quality measures do not include task information, we propose a measure which takes into account user experience. Experiments have been performed in a virtual environment that enables real-time human interaction by means of a dataglove and a motion tracker. Also, a local grasp optimization technique is described to amend uncertainties arising from user demonstration. Finally, the grasp quality measure has been applied for synthesizing manipulation tasks with a simulated robot arm.